© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 76843
    Prev
    Next
    INDEX
    Explanations

    questions that seek clarification or assessment of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    question starters

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects interrogative cues—tokens that signal a question or the start of a question phrase.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MaterialApp
    -0.41
    parsedMessage
    -0.40
     ſta
    -0.39
     dieß
    -0.36
     diſt
    -0.35
     ſur
    -0.35
     viſ
    -0.33
     ſaid
    -0.31
     giáo
    -0.30
     poffe
    -0.30
    POSITIVE LOGITS
    ContentAsync
    0.58
    +:+
    0.56
    ParallelGroup
    0.54
    AndEndTag
    0.51
    djangoproject
    0.50
     оригіналу
    0.48
    ፩
    0.48
     ExecuteAsync
    0.47
     autorytatywna
    0.47
     المعيارى
    0.46
    Activations Density 0.120%

    No Known Activations